metadata
env_name: CartPole-v1
tags:
- CartPole-v1
- a2c-gae
- reinforcement-learning
- custom-implementation
- policy-gradient
- pytorch
- a2c
- gae
model-index:
- name: A2C-GAE-CartPoleV1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 499.94 +/- 0.42
name: mean_reward
verified: false
A2C-GAE Agent playing CartPole-v1
This is a trained model of a A2C-GAE agent playing CartPole-v1.
Usage
create the conda env in https://github.com/GeneHit/drl_practice
conda create -n drl python=3.10
conda activate drl
python -m pip install -r requirements.txt
play with full model
# load the full model
model = load_from_hub(repo_id="winkin119/A2C-GAE-CartPoleV1", filename="full_model.pt")
# Create the environment.
env = gym.make("CartPole-v1")
state, _ = env.reset()
action = model.action(state)
...
There is also a state dict version of the model, you can check the corresponding chapter in the repo.